© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8681
    Prev
    Next
    INDEX
    Explanations

    The neuron is keyed to words and phrases related to shopping and retail commerce (e.g., shop, shopping, store, market).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.75
    개발
    0.70
    入射
    0.64
    reg
    0.61
    ект
    0.61
     Niv
    0.61
    EVENTS
    0.60
     aeruginosa
    0.59
     കാരണ
    0.59
    
    0.58
    POSITIVE LOGITS
     магазине
    1.81
    商店
    1.80
    购物
    1.76
     магазин
    1.75
     магазина
    1.74
     ร้าน
    1.72
     দোকানে
    1.71
     shopping
    1.70
     магази
    1.68
     retailers
    1.67
    Activations Density 1.852%

    No Known Activations